PLAY PODCASTS
Seventy3

Seventy3

任雨山

786 episodesZH-CN

Show overview

Seventy3 has been publishing since 2024, and across the 2 years since has built a catalogue of 786 episodes. That works out to roughly 230 hours of audio in total. Releases follow a near-daily cadence.

Episodes typically run ten to twenty minutes — most land between 14 min and 21 min — though episode length varies meaningfully from one episode to the next. None of the episodes are flagged explicit by the publisher. It is catalogued as a ZH-CN-language Technology show.

The show is actively publishing — the most recent episode landed 2 days ago, with 323 episodes already out so far this year. Published by 任雨山.

Episodes
786
Running
2024–2026 · 2y
Median length
18 min
Cadence
Near-daily

From the publisher

73播客,名字取材于Sheldon最喜欢的数字,内容由NotebookLM生成,每天跟随AI读AI业界论文。

Latest Episodes

View all 786 episodes

【第779期】Colosseum:数学与理论计算机科学的长时段研究多智能体框架

Nov 17, 202614 min

【第778期】SoL-Pi:递归扩展代理研究循环以实现高效的 harness

Nov 16, 202614 min

【第777期】字节模型蒸馏与扩展规律研究

Nov 15, 202618 min

【第776期】Dream-RSI:基于演化世界的递归自我改进框架

Nov 14, 202618 min

【第775期】Codebook Agent:AI协作只需六种核心结构

Nov 13, 202614 min

【第774期】面向写作的灵动思辨伙伴设计

Nov 12, 202619 min

【第773期】ParSer:大模型智能体的并行阅读与深度推理

Nov 11, 202619 min

【第772期】SMART:以设计文档为核心的AI原生性能建模工具

Nov 10, 202620 min

【第771期】STAIR:利用目录结构提升长文档检索精度

Nov 9, 202628 min

【第770期】FrogNano:在线任务合成助力4B编程智能体训练

Nov 8, 202617 min

【第769期】过程图:大语言模型智能体的自进化执行架构

Nov 8, 202621 min

【第768期】AI研究偏好模型:驱动研究智能体高效实验

Nov 6, 202627 min

【第767期】E-Commerce Bench:大模型自主经营能力评估 benchmark

Nov 5, 202615 min

【第766期】CORAL:基于大模型代理循环的推荐系统优化优化器

Nov 4, 202611 min

【第765期】SKILL.state:具有显式执行状态的可扩展长程智能体技能

Nov 3, 202618 min

【第764期】WikiSkill:通过持久知识演化提升智能体技能

Nov 2, 202623 min

【第763期】Harness-of-Harness:基于LLM的自动化游戏开发框架

Nov 1, 202614 min

【第762期】声明性注意机制:大模型自主控制注意力跨度

Oct 31, 202617 min

【第761期】Co-Scientist:Gemini驱动的现实世界科研加速器

Oct 30, 202620 min

【第760期】超越压缩悬崖:AI智能体的知识分流框架

Oct 29, 202614 min
任雨山@小宇宙App